Building Graph Representations of Deep Vector Embeddings

Abstract

Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector embedding spaces, which enables the use of traditional machine learning algorithms on top of them. In this short paper we propose the construction of a graph embedding space instead, introducing a methodology to transform the knowledge coded within a deep convolutional network into a topological space (i.e. a network). We outline how such graph can hold data instances, data features, relations between instances and features, and relations among features. Finally, we introduce some preliminary experiments to illustrate how the resultant graph embedding space can be exploited through graph analytics algorithms.

Accepted at the 2nd Workshop on Semantic Deep Learning (SemDeep-2)

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• Deep Convolutional Features for Image Based Retrieval and Scene Categorization
• Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
• An Out-of-the-box Full-network Embedding for Convolutional Neural Networks
• Fluid Communities: A Competitive, Scalable and Diverse Community Detection Algorithm
• On the Behavior of Convolutional Nets for Feature Extraction